platform-sharing-owd-configure

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). In SKILL.md Phase 1 Step 1-2 the agent queries the Salesforce Tooling API for EntityDefinition filtered by a user-supplied <ObjectName> (or returns all customizable objects), but the only LLM-readable text ingested at runtime is Salesforce-managed fields, not arbitrary outsider-authored free text submitted into a monitored queue/feed.